A couple of months ago, we announced that over 50 Google-managed MCP servers are available.
Today, we’ll dive into how to use the Gemini Enterprise Agent Platform remote MCP server to securely connect your external AI agents to the resources inside your Google Cloud environment.
Think of the Agent Platform MCP server as a bridge between your favorite external development tools and your Google Cloud architecture.
If you are building an agent in Antigravity CLI or Claude Code, for example, the Agent Platform MCP server allows that agent to securely interact with your Agent Platform resources. That way, your agent can now easily call models from Model Garden, pull down shared prompt templates, or even manage Notebooks directly within your project – all without ever leaving the IDE. The speed at which you deliver value is one of your greatest advantages. But sometimes, connecting external development environments to cloud infrastructure forces a trade-off. Developers want to move fast with minimal setup, while IT teams need strict governance over data access.
The Agent Platform MCP server provides a single, standardized interface for your external agents so you can spend less time writing integration code and more time building useful features. And by running entirely within Google Cloud’s secure infrastructure, it gives you ready-to-use endpoints that protect your data while accelerating your development.
Get the best of both worlds:
Enable the API: The Gemini Enterprise Agent Platform remote MCP server is automatically enabled when you enable the Gemini Enterprise Agent Platform API within your Google Cloud project.
-
Configure your client: Connect your AI application by following our configuration instructions to point to the remote server.
-
Use toolsets: Access a robust, copyable list of Toolset Endpoints to begin interacting with your Agent Platform resources immediately.
| | || | | | | | /mcp/generate | Generative AI tools | Core generation features | | /mcp/predict | Prediction tools | Inference and raw prediction | | /mcp/notebook | Colab enterprise notebook tools | Notebook runtime and execution management | | /mcp/endpoints | Endpoint management tools | Lifecycle management for model endpoints | | /mcp/models | Model registry tools | Model upload, registry, and deployment | | /mcp/tuning | Model fine-tuning tools | Finetuning job management and tracking | | /mcp/evaluation | Quality evaluation tools | Automated model quality and instance evaluation | | /mcp/prompts | Prompt management tools | Prompt engineering and versioning workflows |
Visit the Agent Platform page to connect your favorite agent frameworks to the Agent Platform MCP server and start building today.